Ders Planı

CLASS 1

Lesson plan /

Lesson Information

Course Credit
Course ECTS Credit
Teaching Language of Instruction	İngilizce
Level of Course	Bachelor's Degree, TYYÇ: Level 6, EQF-LLL: Level 6, QF-EHEA: First Cycle
Type of Course
Mode of Delivery	Face-to-face
Does the course require compulsory or optional work experience?
Course Coordinator	Prof. Dr. RAFET AKDENİZ
Instructor (s)
Course Assistant

Purpose and Content

The aim of the course	This introductory course gives an overview of many concepts, techniques, and algorithms in machine learning, beginning with topics such as classification and linear regression and ending up with more recent topics such as boosting, support vector machines, hidden Markov models, and Bayesian networks. The course will give the student the basic ideas and intuition behind modern machine learning methods as well as a bit more formal understanding of how, why, and when they work. The underlying theme in the course is statistical inference as it provides the foundation for most of the methods covered.
Course Content	It will cover some of the main models and algorithms for regression, classification, clustering and probabilistic classification. Topics such as linear and logistic regression, regularisation, probabilistic (Bayesian) inference, SVMs and neural networks, clustering and dimensionality reduction. The module will use primarily the Python programming language and assumes familiarity with linear algebra, probability theory, and programming in Python.

The aim of the course

This introductory course gives an overview of many concepts, techniques, and algorithms in machine learning, beginning with topics such as classification and linear regression and ending up with more recent topics such as boosting, support vector machines, hidden Markov models, and Bayesian networks. The course will give the student the basic ideas and intuition behind modern machine learning methods as well as a bit more formal understanding of how, why, and when they work. The underlying theme in the course is statistical inference as it provides the foundation for most of the methods covered.

Course Content

It will cover some of the main models and algorithms for regression, classification, clustering and probabilistic classification. Topics such as linear and logistic regression, regularisation, probabilistic (Bayesian) inference, SVMs and neural networks, clustering and dimensionality reduction. The module will use primarily the Python programming language and assumes familiarity with linear algebra, probability theory, and programming in Python.

Learning Outcomes

Adequate knowledge in mathematics, physical sciences and the computer engineering subjects of individual branches; the ability to implement theoretical and practical knowledge in the respective areas to modeling and solving computer engineering problems.
Ability to reflect the developments in Information and Communication Technologies to the applications of Information Technology.
Ability to identify, define, formulate and solve complex computer engineering problems; ability to select and implement the appropriate analysis and modeling methods in this respect.
Ability to design experiments for analysing computer engineering problems, to conduct experiments, to collect data, to analyse and interpret the results.
Ability to design a complex informtacis system, process, device or product to meet specific requirements under realistic restrictions and conditions; ability to implement the modern design methods for this purpose.
Ability to use, choose and develop modern techniques and means required for computer engineering applications; ability to use information technologies effectively.
Ability to work effectively in interdisciplinary and multi-disciplinary teams; ability to work individually..
Knowledge of applications in business life like project management, risk management and change management; awareness about entrepreneurship, innovativeness and sustainable development.
Awareness of the necessity of lifelong learning; ability to reach information, follow the latest developments in science and technology; ability to ensure self-renewal perpetually.
Ability to communicate efficiently both in oral and written ways in Turkish; knowledge of at least one foreign language; ability to effectively prepare reports and understand written reports, prepare design and production reports, effective presentation, giving and receiving clear and understandable instructions.
Knowledge on the effects of informatics applications on health, environment and safety in terms of universal and social aspects and information about the problems of the era; awareness on the legal results of informatics solutions.
Acting in line with ethical principles, sense of professional and ethical responsibility; knowledge on the standards of engineering applications.

Weekly Course Subjects

1	Introduction to Machine Learning and Supervised Learning
2	Linear Regression
3	Linear Classification
4	Basis Expansions and Regularization
5	Decision Trees and Related Methods
6	Model Assessment and Selection
7	Neural Networks
8	Midterm Exam
9	Random Forests and Boosting
10	Support Vector Machines
11	Unsupervised Learning
12	Reinforcement Learning
13	Learning Theory
14	Learning Theory

Resources

T1 Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong, Mathematics for Machine Learning,

Cambridge University Press (23 April 2020)

T2 Tom M. Mitchell- Machine Learning - McGraw Hill Education, International Edition

T3 Aurélien Géron Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly

Media, Inc. 2nd Edition

R1 Ian Goodfellow, Yoshoua Bengio, and Aaron Courville Deep Learning MIT Press Ltd,

Illustrated edition

R2 Christopher M. Bishop Pattern Recognition and Machine Learning - Springer, 2nd edition

R3 Trevor Hastie, Robert Tibshirani, and Jerome Friedman - The Elements of

Statistical Learning: Data Mining, Inference, and Prediction - Springer, 2nd edition

CLASS 1

CLASS 2

CLASS 3

CLASS 4

Lesson Information

Purpose and Content

Learning Outcomes

Weekly Course Subjects

Resources

ABOUT IAU

COMMITTEE

PUBLICATIONS

MEDIA CENTER